get_navmesh_bake_state

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are supplied, so the description carries the full disclosure burden, and it discloses almost nothing. The 'get' prefix implies a read-only inspection, but the description never confirms it, never says whether it scans the whole project or costs time on large projects, and never clarifies what 'agent script hits' means operationally. An agent has no behavioral footing beyond the topic.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One short fragment, front-loaded and free of filler, which is good. However, the compression crosses into ambiguity: 'settings presence' and 'agent script hits' are internal shorthand whose meaning is not recoverable from the sentence.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations, no output schema, and no parameters, the description is the only source of information, and it is a nine-word fragment. An agent cannot tell what the response looks like, whether missing markers count as a failure, or how this differs from other project-inspection tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The listed output facets (markers, settings, script hits) at least hint at what the parameterless call will surface.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the resource (NavMesh bake state) and lists the three things it reports: scenes with NavMesh markers, settings presence, agent script hits. That is more specific than a tautology, but it is a noun-phrase fragment with no verb, so what the tool actually does (scan, aggregate, report) must be inferred from the name. It is not differentiated from siblings such as get_broken_asset_refs or get_animator_states beyond subject matter.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance at all: no preconditions, no indication of when a NavMesh bake diagnosis is warranted, and no mention of any alternative or follow-up tool. The agent must guess the scenario from the tool name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.